deepspeed_z3.yaml

compute_environment: LOCAL_MACHINE                                                                                                                                                                     
debug: false                                                                                                                                                                                           
deepspeed_config:
  deepspeed_multinode_launcher: standard
  gradient_accumulation_steps: 1
  gradient_clipping: 1.0
  offload_optimizer_device: cpu
  offload_param_device: cpu
  zero3_init_flag: true
  zero3_save_16bit_model: false
  zero_stage: 3
distributed_type: DEEPSPEED
downcast_bf16: 'no'
enable_cpu_affinity: false
machine_rank: 0
main_process_ip: localhost
main_process_port: 999
main_training_function: main
mixed_precision: bf16
num_machines: 1
num_processes: 8
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false